Investigation Into Recognition Algorithm of Helmet Violation Based on YOLOv5-CBAM-DCN

Wang, Lijun; Cao, Yunyu; Wang, Song; Song, Xiaona; Zhang, Shenfeng; Zhang, Jianyong; Niu, Jinxing

doi:10.1109/access.2022.3180796

Cited by 41 publications

(17 citation statements)

References 23 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper proposes a deep learning method for detecting safety helmet wearing on construction sites, achieving 92.2% mean average precision with high speed and accuracy using multi-scale features. Investigation Into Recognition Algorithm of Helmet Violation Based on YOLOv5-CBAM-DCN, 2022 [18]. This paper presents an enhanced YOLOv5-based method for recognizing safety helmet violations, addressing challenges like complex backgrounds, dense targets, and irregular helmet shapes, achieving 91.6% accuracy at 29 fps.…”

Section: IImentioning

confidence: 99%

Implementing Improved YOLOv5s for Immediate Identification of Helmetless Forklift Drivers

Sheeba,

Singh,

Karan

et al. 2024

IJRASET

View full text Add to dashboard Cite

Construction workers are exposed to a multitude of health and safety risks on job sites. Despite authorities' repeated efforts to enhance safety management, incidents persist, negatively impacting both worker well-being and project progress. Therefore, it is imperative to devise effective strategies aimed at improving construction site safety management. Currently, one of the challenges in ensuring safety is the lack of a more precise method for detecting objects, particularly safety helmets. To address this issue, techniques such as Generalized Intersection Over Union (GIOU) and Soft Non-Maximum Suppression (SoftNMS) are employed to refine the regression mechanism of bounding boxes. Furthermore, advancements have been made in training the Faster RCNN model using a multiscale approach, thereby enhancing its overall robustness.

show abstract

Section: IImentioning

confidence: 99%

Implementing Improved YOLOv5s for Immediate Identification of Helmetless Forklift Drivers

Sheeba,

Singh,

Karan

et al. 2024

IJRASET

View full text Add to dashboard Cite

show abstract

“…Conventional convolution fuses all channels of the input feature map, and the network cannot focus on important feature channels. In contrast, FEBlock can adjust the distribution of weights, enhance useful features and suppress useless information [26]. When different scale feature maps are input, the model can adaptively adjust the size of the receiving domain of the small target in the UAV capture scene to improve the object detection performance of the model.…”

Section: B Improvements In Spatial Pyramidal Poolingmentioning

confidence: 99%

An Improved YOLOv5 Method for Small Object Detection in UAV Capture Scenes

et al. 2023

View full text Add to dashboard Cite

Aiming at the problem of a large number of small dense objects in high-altitude shooting and complex background noise interference in the captured scenes, an improved object detection algorithm for YOLOv5 UAV capture scenes is proposed. A Feature Enhancement Block (FEBlock) is first proposed to generate adaptive weights for different receptive field features by convolution, assigning major weights to shallow feature maps to improve small object feature extraction ability. The FEBlock is then integrated into Spatial Pyramid Pooling (SPP) to generate Enhanced Spatial Pyramid Pooling (ESPP), which performs feature enhancement for the result of each maximum pooling; and creates new features containing multiscale contextual information with better feature characterization capability by weighting fused contextual features. Secondly, the Self-Characteristic Expansion Plate (SCEP) is proposed, which achieves the fusion and expansion of feature information through compression, non-linear mapping, and expansion with its own module, further improving the network's capacity for feature extraction and generating a new spatial pyramid pooling (ESPP-S) by splicing with ESPP. Finally, a shallower feature map is added as a detection layer to the YOLOv5 network model's large, medium, and small detection layers to improve the network's detection performance for medium and long-range objects. Experiments were conducted on the VisDrone2021 dataset, and the results showed that the improved YOLOv5 model improved mAP0.5 by 4.6%, mAP0.5:0.95 by 2.9%, and precision by 2.7%. The mAP0.5 of the model trained at the input resolution of 1024 × 1024 reached 56.8%. The experiments show that the improved YOLOv5 model can improve object detection accuracy for UAV capture scenes.

show abstract

“…The head utilizes anchor-based object detection, where each anchor box detects a specific object. Moreover, the model utilizes the GIoU Loss [13] to estimate the recognition loss associated with the detected bounding boxes. [14] is an efficient convolutional neural network designed to be lightweight.…”

Section: Yolov5s Backbone Network Lightweight Improvementsmentioning

confidence: 99%

Research on a New Method of Track Turnout Identification Based on Improved Yolov5s

Chen

Tian

et al. 2023

Processes

View full text Add to dashboard Cite

The modern tram track automatic cleaning car is a crucial equipment in urban rail transportation systems, effectively removing trash, dust, and other debris from the slotted tracks of trams. However, due to the complex and variable structure of turnouts, the cleaning car often requires assistance in accurately detecting their positions. Consequently, the cleaning car needs help in adequately cleaning or bypassing turnouts, which adversely affects cleaning effectiveness and track maintenance quality. This paper presents a novel method for tracking turnout identification called PBE-YOLO based on the improved yolov5s framework. The algorithm enhances yolov5s by optimizing the lightweight backbone network, improving feature fusion methods, and optimizing the regression loss function. The proposed method is trained using a dataset of track turnouts collected through field shots on modern tram lines. Comparative experiments are conducted to analyze the performance of the improved lightweight backbone network, as well as performance comparisons and ablation experiments for the new turnout identification method. Experimental results demonstrate that the proposed PBE-YOLO method achieves a 52.71% reduction in model parameters, a 4.60% increase in mAP@0.5(%), and a 3.27% improvement in precision compared to traditional yolov5s. By improving the track turnout identification method, this paper enables the automatic cleaning car to identify turnouts’ positions accurately. This enhancement leads to several benefits, including increased automation levels, improved cleaning efficiency and quality, reduced reliance on manual intervention, and mitigation of collision risks between the cleaning car and turnouts.

show abstract

Investigation Into Recognition Algorithm of Helmet Violation Based on YOLOv5-CBAM-DCN

Cited by 41 publications

References 23 publications

Implementing Improved YOLOv5s for Immediate Identification of Helmetless Forklift Drivers

Implementing Improved YOLOv5s for Immediate Identification of Helmetless Forklift Drivers

An Improved YOLOv5 Method for Small Object Detection in UAV Capture Scenes

Research on a New Method of Track Turnout Identification Based on Improved Yolov5s

Contact Info

Product

Resources

About